linux-stable/arch/x86/kernel/module.c
Linus Torvalds 7001052160 Add support for Intel CET-IBT, available since Tigerlake (11th gen), which is a
coarse grained, hardware based, forward edge Control-Flow-Integrity mechanism
 where any indirect CALL/JMP must target an ENDBR instruction or suffer #CP.
 
 Additionally, since Alderlake (12th gen)/Sapphire-Rapids, speculation is
 limited to 2 instructions (and typically fewer) on branch targets not starting
 with ENDBR. CET-IBT also limits speculation of the next sequential instruction
 after the indirect CALL/JMP [1].
 
 CET-IBT is fundamentally incompatible with retpolines, but provides, as
 described above, speculation limits itself.
 
 [1] https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/branch-history-injection.html
 -----BEGIN PGP SIGNATURE-----
 
 iQJJBAABCgAzFiEEv3OU3/byMaA0LqWJdkfhpEvA5LoFAmI/LI8VHHBldGVyekBp
 bmZyYWRlYWQub3JnAAoJEHZH4aRLwOS6ZnkP/2QCgQLTu6oRxv9O020CHwlaSEeD
 1Hoy3loum5q5hAi1Ik3dR9p0H5u64c9qbrBVxaFoNKaLt5GKrtHaDSHNk2L/CFHX
 urpH65uvTLxbyZzcahkAahoJ71XU+m7PcrHLWMunw9sy10rExYVsUOlFyoyG6XCF
 BDCNZpdkC09ZM3vwlWGMZd5Pp+6HcZNPyoV9tpvWAS2l+WYFWAID7mflbpQ+tA8b
 y/hM6b3Ud0rT2ubuG1iUpopgNdwqQZ+HisMPGprh+wKZkYwS2l8pUTrz0MaBkFde
 go7fW16kFy2HQzGm6aIEBmfcg0palP/mFVaWP0zS62LwhJSWTn5G6xWBr3yxSsht
 9gWCiI0oDZuTg698MedWmomdG2SK6yAuZuqmdKtLLoWfWgviPEi7TDFG/cKtZdAW
 ag8GM8T4iyYZzpCEcWO9GWbjo6TTGq30JBQefCBG47GjD0csv2ubXXx0Iey+jOwT
 x3E8wnv9dl8V9FSd/tMpTFmje8ges23yGrWtNpb5BRBuWTeuGiBPZED2BNyyIf+T
 dmewi2ufNMONgyNp27bDKopY81CPAQq9cVxqNm9Cg3eWPFnpOq2KGYEvisZ/rpEL
 EjMQeUBsy/C3AUFAleu1vwNnkwP/7JfKYpN00gnSyeQNZpqwxXBCKnHNgOMTXyJz
 beB/7u2KIUbKEkSN
 =jZfK
 -----END PGP SIGNATURE-----

Merge tag 'x86_core_for_5.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 CET-IBT (Control-Flow-Integrity) support from Peter Zijlstra:
 "Add support for Intel CET-IBT, available since Tigerlake (11th gen),
  which is a coarse grained, hardware based, forward edge
  Control-Flow-Integrity mechanism where any indirect CALL/JMP must
  target an ENDBR instruction or suffer #CP.

  Additionally, since Alderlake (12th gen)/Sapphire-Rapids, speculation
  is limited to 2 instructions (and typically fewer) on branch targets
  not starting with ENDBR. CET-IBT also limits speculation of the next
  sequential instruction after the indirect CALL/JMP [1].

  CET-IBT is fundamentally incompatible with retpolines, but provides,
  as described above, speculation limits itself"

[1] https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/branch-history-injection.html

* tag 'x86_core_for_5.18_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  kvm/emulate: Fix SETcc emulation for ENDBR
  x86/Kconfig: Only allow CONFIG_X86_KERNEL_IBT with ld.lld >= 14.0.0
  x86/Kconfig: Only enable CONFIG_CC_HAS_IBT for clang >= 14.0.0
  kbuild: Fixup the IBT kbuild changes
  x86/Kconfig: Do not allow CONFIG_X86_X32_ABI=y with llvm-objcopy
  x86: Remove toolchain check for X32 ABI capability
  x86/alternative: Use .ibt_endbr_seal to seal indirect calls
  objtool: Find unused ENDBR instructions
  objtool: Validate IBT assumptions
  objtool: Add IBT/ENDBR decoding
  objtool: Read the NOENDBR annotation
  x86: Annotate idtentry_df()
  x86,objtool: Move the ASM_REACHABLE annotation to objtool.h
  x86: Annotate call_on_stack()
  objtool: Rework ASM_REACHABLE
  x86: Mark __invalid_creds() __noreturn
  exit: Mark do_group_exit() __noreturn
  x86: Mark stop_this_cpu() __noreturn
  objtool: Ignore extra-symbol code
  objtool: Rename --duplicate to --lto
  ...
2022-03-27 10:17:23 -07:00

320 lines
7.9 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/* Kernel module help for x86.
Copyright (C) 2001 Rusty Russell.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/moduleloader.h>
#include <linux/elf.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/kasan.h>
#include <linux/bug.h>
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/jump_label.h>
#include <linux/random.h>
#include <linux/memory.h>
#include <asm/text-patching.h>
#include <asm/page.h>
#include <asm/setup.h>
#include <asm/unwind.h>
#if 0
#define DEBUGP(fmt, ...) \
printk(KERN_DEBUG fmt, ##__VA_ARGS__)
#else
#define DEBUGP(fmt, ...) \
do { \
if (0) \
printk(KERN_DEBUG fmt, ##__VA_ARGS__); \
} while (0)
#endif
#ifdef CONFIG_RANDOMIZE_BASE
static unsigned long module_load_offset;
/* Mutex protects the module_load_offset. */
static DEFINE_MUTEX(module_kaslr_mutex);
static unsigned long int get_module_load_offset(void)
{
if (kaslr_enabled()) {
mutex_lock(&module_kaslr_mutex);
/*
* Calculate the module_load_offset the first time this
* code is called. Once calculated it stays the same until
* reboot.
*/
if (module_load_offset == 0)
module_load_offset =
(get_random_int() % 1024 + 1) * PAGE_SIZE;
mutex_unlock(&module_kaslr_mutex);
}
return module_load_offset;
}
#else
static unsigned long int get_module_load_offset(void)
{
return 0;
}
#endif
void *module_alloc(unsigned long size)
{
gfp_t gfp_mask = GFP_KERNEL;
void *p;
if (PAGE_ALIGN(size) > MODULES_LEN)
return NULL;
p = __vmalloc_node_range(size, MODULE_ALIGN,
MODULES_VADDR + get_module_load_offset(),
MODULES_END, gfp_mask,
PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE,
__builtin_return_address(0));
if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
vfree(p);
return NULL;
}
return p;
}
#ifdef CONFIG_X86_32
int apply_relocate(Elf32_Shdr *sechdrs,
const char *strtab,
unsigned int symindex,
unsigned int relsec,
struct module *me)
{
unsigned int i;
Elf32_Rel *rel = (void *)sechdrs[relsec].sh_addr;
Elf32_Sym *sym;
uint32_t *location;
DEBUGP("Applying relocate section %u to %u\n",
relsec, sechdrs[relsec].sh_info);
for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
/* This is where to make the change */
location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+ rel[i].r_offset;
/* This is the symbol it is referring to. Note that all
undefined symbols have been resolved. */
sym = (Elf32_Sym *)sechdrs[symindex].sh_addr
+ ELF32_R_SYM(rel[i].r_info);
switch (ELF32_R_TYPE(rel[i].r_info)) {
case R_386_32:
/* We add the value into the location given */
*location += sym->st_value;
break;
case R_386_PC32:
case R_386_PLT32:
/* Add the value, subtract its position */
*location += sym->st_value - (uint32_t)location;
break;
default:
pr_err("%s: Unknown relocation: %u\n",
me->name, ELF32_R_TYPE(rel[i].r_info));
return -ENOEXEC;
}
}
return 0;
}
#else /*X86_64*/
static int __apply_relocate_add(Elf64_Shdr *sechdrs,
const char *strtab,
unsigned int symindex,
unsigned int relsec,
struct module *me,
void *(*write)(void *dest, const void *src, size_t len))
{
unsigned int i;
Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;
Elf64_Sym *sym;
void *loc;
u64 val;
DEBUGP("Applying relocate section %u to %u\n",
relsec, sechdrs[relsec].sh_info);
for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
/* This is where to make the change */
loc = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+ rel[i].r_offset;
/* This is the symbol it is referring to. Note that all
undefined symbols have been resolved. */
sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
+ ELF64_R_SYM(rel[i].r_info);
DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info),
sym->st_value, rel[i].r_addend, (u64)loc);
val = sym->st_value + rel[i].r_addend;
switch (ELF64_R_TYPE(rel[i].r_info)) {
case R_X86_64_NONE:
break;
case R_X86_64_64:
if (*(u64 *)loc != 0)
goto invalid_relocation;
write(loc, &val, 8);
break;
case R_X86_64_32:
if (*(u32 *)loc != 0)
goto invalid_relocation;
write(loc, &val, 4);
if (val != *(u32 *)loc)
goto overflow;
break;
case R_X86_64_32S:
if (*(s32 *)loc != 0)
goto invalid_relocation;
write(loc, &val, 4);
if ((s64)val != *(s32 *)loc)
goto overflow;
break;
case R_X86_64_PC32:
case R_X86_64_PLT32:
if (*(u32 *)loc != 0)
goto invalid_relocation;
val -= (u64)loc;
write(loc, &val, 4);
#if 0
if ((s64)val != *(s32 *)loc)
goto overflow;
#endif
break;
case R_X86_64_PC64:
if (*(u64 *)loc != 0)
goto invalid_relocation;
val -= (u64)loc;
write(loc, &val, 8);
break;
default:
pr_err("%s: Unknown rela relocation: %llu\n",
me->name, ELF64_R_TYPE(rel[i].r_info));
return -ENOEXEC;
}
}
return 0;
invalid_relocation:
pr_err("x86/modules: Skipping invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), loc, val);
return -ENOEXEC;
overflow:
pr_err("overflow in relocation type %d val %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), val);
pr_err("`%s' likely not compiled with -mcmodel=kernel\n",
me->name);
return -ENOEXEC;
}
int apply_relocate_add(Elf64_Shdr *sechdrs,
const char *strtab,
unsigned int symindex,
unsigned int relsec,
struct module *me)
{
int ret;
bool early = me->state == MODULE_STATE_UNFORMED;
void *(*write)(void *, const void *, size_t) = memcpy;
if (!early) {
write = text_poke;
mutex_lock(&text_mutex);
}
ret = __apply_relocate_add(sechdrs, strtab, symindex, relsec, me,
write);
if (!early) {
text_poke_sync();
mutex_unlock(&text_mutex);
}
return ret;
}
#endif
int module_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *me)
{
const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
*para = NULL, *orc = NULL, *orc_ip = NULL,
*retpolines = NULL, *ibt_endbr = NULL;
char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
if (!strcmp(".text", secstrings + s->sh_name))
text = s;
if (!strcmp(".altinstructions", secstrings + s->sh_name))
alt = s;
if (!strcmp(".smp_locks", secstrings + s->sh_name))
locks = s;
if (!strcmp(".parainstructions", secstrings + s->sh_name))
para = s;
if (!strcmp(".orc_unwind", secstrings + s->sh_name))
orc = s;
if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
orc_ip = s;
if (!strcmp(".retpoline_sites", secstrings + s->sh_name))
retpolines = s;
if (!strcmp(".ibt_endbr_seal", secstrings + s->sh_name))
ibt_endbr = s;
}
/*
* See alternative_instructions() for the ordering rules between the
* various patching types.
*/
if (para) {
void *pseg = (void *)para->sh_addr;
apply_paravirt(pseg, pseg + para->sh_size);
}
if (retpolines) {
void *rseg = (void *)retpolines->sh_addr;
apply_retpolines(rseg, rseg + retpolines->sh_size);
}
if (alt) {
/* patch .altinstructions */
void *aseg = (void *)alt->sh_addr;
apply_alternatives(aseg, aseg + alt->sh_size);
}
if (ibt_endbr) {
void *iseg = (void *)ibt_endbr->sh_addr;
apply_ibt_endbr(iseg, iseg + ibt_endbr->sh_size);
}
if (locks && text) {
void *lseg = (void *)locks->sh_addr;
void *tseg = (void *)text->sh_addr;
alternatives_smp_module_add(me, me->name,
lseg, lseg + locks->sh_size,
tseg, tseg + text->sh_size);
}
/* make jump label nops */
jump_label_apply_nops(me);
if (orc && orc_ip)
unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
(void *)orc->sh_addr, orc->sh_size);
return 0;
}
void module_arch_cleanup(struct module *mod)
{
alternatives_smp_module_del(mod);
}